© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 119037
    Prev
    Next
    INDEX
    Explanations

    911, 811, 11

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     you
    -1.88
     that
    -1.72
     we
    -1.66
     If
    -1.47
    this
    -1.44
     THIS
    -1.42
     $
    -1.38
     I
    -1.38
     This
    -1.34
     mientras
    -1.32
    POSITIVE LOGITS
     captiv
    1.49
    饜
    1.48
    卣
    1.48
    鶿
    1.47
    
    1.45
    鴆
    1.41
    喁
    1.40
    ゅう
    1.39
     ſch
    1.39
    
    1.37
    Activations Density 0.008%

    No Known Activations